© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6573
    Prev
    Next
    INDEX
    Explanations

    website usernames and profile information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    601
    +0.14
    0.4%
    656
    +0.14
    0.4%
    22
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.14
    0.02
    22
    +0.14
    0.03
    469
    +0.12
    0.02
    Negative Logits
    ouf
    -1.09
     Foley
    -1.03
    erness
    -0.98
    ider
    -0.92
    andro
    -0.92
    ogyn
    -0.92
    ÄŁ
    -0.91
    URR
    -0.91
    yk
    -0.90
    oÄŁ
    -0.90
    POSITIVE LOGITS
    romeda
    1.19
    76561
    1.08
    çİĭ
    1.08
    Posts
    1.04
     Joined
    0.97
    Attempts
    0.96
    ãĤ´ãĥ³
    0.93
     Knights
    0.88
     Atomic
    0.88
    manent
    0.87
    Activations Density 0.222%

    No Known Activations